Havuz

Compile your own LLM for the Hailo-10H — an open pipeline from Hugging Face checkpoint to a self-contained HEF, served with hailo-ollama.

A scientific-method runtime for AI agents: hypotheses, experiments, evidence, provenance, reproducibility, and auditable conclusions.

数学建模项目与资料库：竞赛论文、可运行代码、历年赛题、优秀论文与常用模型案例

The complete cookbook for Jev by TypeSafe AI — 120+ use cases, 10 runnable examples, 4 composition patterns, and first-principles theory for

One API for every LLM: 170+ providers through one client, with a Rust core and native bindings for every major language.

🌟 推理王国：关于 AI 推理机制的思想实验手册。从信息论、符号逻辑与表示学习出发，系统剖析大模型“智能”的本质。

🤖 AI Agent-driven Kaggle competition workflow. Battle-tested patterns for score stabilization, submission troubleshooting, kernel workflows,

Flash weight streaming for MLX: run massive models larger than your RAM on Apple Silicon.

Top Dynamic AI World Simulation & Storytelling Tools 2026

GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.

🦀 Decoder-only LLM built from scratch in pure Rust using Candle — no Python, no PyTorch. Gated DeltaNet + sparse attention, fine-grained MoE

Free open source disk cleaner for developers. Clean Hugging Face, Ollama, npm, pip, conda, Docker caches, app leftovers, and junk files on m

🌹 Rose: Range-Of-Slice Equilibration PyTorch optimizer. Stateless optimization through range-normalized gradient updates.

GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, depl

44 plug-and-play skills for OpenClaw — self-modifying AI agent with cron scheduling, security guardrails, persistent memory, knowledge graph

Self-tuning multi-agent AI trading system. 8-source signal fusion, Bull/Bear/Judge debate on Claude Opus 4.7, Kelly + ATR position sizing. P

Take the 100 Days of AI challenge - learn one AI concept a day, from machine learning basics to AI agents in production, in 100 days.

Strands-based agents and harnesses for agentic benchmarks.

Best AI Workload Orchestrator for Kubernetes Python 2026

Meet Reviewer 2 before they meet you ！ A Claude Code skill that red-teams your paper draft — a simulated peer-review panel + an evidence

Run AI models on Apple Silicon and Raspberry Pi

End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking cur

📊 Daily auto-updated snapshots of all Arena AI (LMSYS Chatbot Arena) leaderboards — LLM, Vision, Code, Video, Image & more. Structured JSON

Data science and Machine Learning AI agent

AI-powered deepfake detector that classifies uploaded face images and videos as Real or Fake with confidence scores. Full-stack app built wi

A refined, premium landing page for Tech Alpha, a modern AI startup brand built to showcase services, projects, portfolio work, and founder

Per-step LLM routing benchmark with 970 static labels, live SWE-bench evaluation, an open data pipeline, and a public leaderboard.

Building an Image-to-Video (I2V) Model from Scratch

Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity simula

A comprehensive hands-on, AI-first Python curriculum with 80+ interactive Jupyter notebooks for AI Engineers from core basics to LLMs, RAG,

STEER — AI4R (AI for Research) experiment framework for auto-research and autonomous research. Connect existing research projects and let an

Independent, evidence-based map of when TypeSafe's Jev actually holds up vs. breaks down — real API-call receipts, not a leaderboard. 中文為主的雙

PASQA: Pitch-Accent-Focused Speech Quality Assessment Model Trained on Synthetic Speech with Accent Errors

The Kimi K3 and DeepSeek-V4-Flash-0731 architectures, reimplemented from scratch in pure Rust (zero dependencies) and verified 1:1 against t

Why is LLM inference slow — and how do you make it fast? A hands-on, first-principles course: roofline → KV cache → quantization → paralleli

LLM inference engine for AMD RDNA4 — Rust + Vulkan compute shaders, gguf & native FP8.

Fugusashi — Federated Learning of LLM Routing with Human-Interpretable Decisions. Open-source alternative to Sakana AI Fugu.

This repository is a comprehensive, hands on roadmap to Python Mastery and AI Engineering. It is designed to take a learner from the very fo

Production-ready RAG assistant for Moodle — containerized with Jenkins CI/CD on AWS.

Qwen3.8-27B on one laptop CPU: up to 2.52 token/s, 8 GB tested, no runtime accuracy loss. Native OpenAI-compatible API with function tools;

AI model that animates any SVG into Lottie with 3-4x fewer tokens than OmniLottie (CVPR 2026). Upload SVG → get animated .lottie. 3B model,

Open-source control layer over PDF parsing that picks the right method, verifies output quality, and falls back automatically when results f

🏆 Real-world problem statements for hackathons & impact projects — curated, structured, and ready to build. 65 problems across 5 tracks: Glo

Tenstorrent backend plugin for vLLM.

A TPU you can watch run - real SystemVerilog systolic array, compiled to WASM, visualized live in your browser.

👻 MoEWatch: A lightweight diagnostic and audit library for Mixture-of-Experts (MoE) models in HuggingFace Transformers — the pytest for MoE

An experimental JEV-powered framework for forecasting short-term stock price direction from structured market data.

The open-source alternative to Suno and ElevenLabs Music. Natural language music composition, run locally, own everything.

Guía gratuita de IA generativa avanzada en español (311 págs.): Transformer, post-entrenamiento, inferencia, GPU, difusión, agentes, segurid

A Personalized Federated Learning (PFL-HCare) framework for IoT healthcare. Features MAML meta-learning, Differential Privacy (RDP), and gra